metadata
library_name: transformers
license: apache-2.0
datasets:
- schneewolflabs/Athanorlite-DPO
base_model:
- nbeerbower/Schreiber-mistral-nemo-12B
Merlina-ORPO-12B
This is the same training run as schneewolflabs/A0l-12B but with a custom ORPO implementation and beta=0.1.
